Home > Research > Publications & Outputs > Spiking neural network training using evolution...
View graph of relations

Spiking neural network training using evolutionary algorithms

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

  • Nicos Pavlidis
  • DK Tasoulis
  • Vassilis P. Plagianakos
  • Michael N. Vrahatis
  • G. Nikiforidis
Publication date2005
Host publicationInternational Joint Conference on Neural Networks (IJCNN 2005)
Number of pages4
ISBN (Print)0-7803-9048-2
<mark>Original language</mark>English


Networks of spiking neurons can perform complex non-linear computations in fast temporal coding just as well as rate coded networks. These networks differ from previous models in that spiking neurons communicate information by the timing, rather than the rate, of spikes. To apply spiking neural networks on particular tasks, a learning process is required. Most existing training algorithms are based on unsupervised Hebbian learning. In this paper, we investigate the performance of the parallel differential evolution algorithm, as a supervised training algorithm for spiking neural networks. The approach was successfully tested on well-known and widely used classification problems.